Variational Shape Completion for Virtual Planning of Jaw Reconstructive Surgery

The premorbid geometry of the mandible is of significant relevance in jaw reconstructive surgeries and occasionally unknown to the surgical team. In this paper, an optimization framework is introduced to train deep models for completion (reconstruction) of the missing segments of the bone based on the remaining healthy structure. To leverage the contextual information of the surroundings of the dissected region, the voxel-weighted Dice loss is introduced. To address the non-deterministic nature of the shape completion problem, we leverage a weighted multi-target probabilistic solution which is an extension to the conditional variational autoencoder (CVAE). This approach considers multiple targets as acceptable reconstructions, each weighted according to their conformity with the original shape. We quantify the performance gain of the proposed method against similar algorithms, including CVAE, where we report statistically significant improvements in both deterministic and probabilistic paradigms. The probabilistic model is also evaluated on its ability to generate anatomically relevant variations for the missing bone. As a unique aspect of this work, the model is tested on real surgical cases where the clinical relevancy of its reconstructions and their compliance with surgeon's virtual plan are demonstrated as necessary steps towards clinical adoption.

[1]  Jan Egger,et al.  Mandibular CT Dataset Collection , 2018 .

[2]  Blake Hannaford,et al.  Evaluation of segmentation methods on head and neck CT: Auto‐segmentation challenge 2015 , 2017, Medical physics.

[3]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[4]  Leonidas J. Guibas,et al.  Representation Learning and Adversarial Generation of 3D Point Clouds , 2017, ArXiv.

[5]  Christopher K. I. Williams,et al.  The shape variational autoencoder: A deep generative model of part‐segmented 3D objects , 2017, Comput. Graph. Forum.

[6]  Carl Kesselman,et al.  The FaceBase Consortium: a comprehensive resource for craniofacial researchers , 2016, Development.

[7]  Purang Abolmaesumi,et al.  AnatomyGen: Deep Anatomy Generation From Dense Representation With Applications in Mandible Synthesis , 2018, MIDL.

[8]  Leonidas J. Guibas,et al.  Learning Representations and Generative Models for 3D Point Clouds , 2017, ICML.

[9]  Alejandro F. Frangi,et al.  A Multi-resolution T-Mixture Model Approach to Robust Group-Wise Alignment of Shapes , 2016, MICCAI.

[10]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[11]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

[12]  Carrie S. Stern,et al.  A Virtual Surgical Planning Algorithm for Delayed Maxillomandibular Reconstruction , 2019, Plastic and reconstructive surgery.

[13]  D. Hidalgo.  Fibula free flap: a new method of mandible reconstruction. , 1989, Plastic and reconstructive surgery.